Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    employee training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Disk
    -0.07
    Additionally
    -0.07
     Nx
    -0.07
    variant
    -0.07
    (xs
    -0.06
    -clock
    -0.06
    -icon
    -0.06
     gas
    -0.06
    981
    -0.06
    mai
    -0.06
    POSITIVE LOGITS
     �
    0.06
    ){//
    0.06
     شر
    0.06
     showAlert
    0.06
     pll
    0.06
    )//
    0.06
     spectator
    0.06
     setHidden
    0.06
    tains
    0.06
     accord
    0.06
    Act Density 0.073%

    No Known Activations